From the 1 of 3 linked papers with an AI index.
3 papers
cs.LG2026
Sparse Inter-Layer Dependencies of Transformer FFN Neurons
Johannes Knittel, Hanspeter Pfister
The paper introduces a training‑free method to attribute the activation of individual feed‑forward network neurons in Transformers to a small set of upstream neuron activations and…
cs.LG2024
GPT-2 Through the Lens of Vector Symbolic Architectures
Johannes Knittel, Tushaar Gangavarapu, Hendrik Strobelt +1
Understanding the general priniciples behind transformer models remains a complex endeavor. Experiments with probing and disentangling features using sparse autoencoders (SAE) sugg…
cs.CV2024
Multimodal Learning for Embryo Viability Prediction in Clinical IVF
Junsik Kim, Zhiyi Shi, Davin Jeong +8
In clinical In-Vitro Fertilization (IVF), identifying the most viable embryo for transfer is important to increasing the likelihood of a successful pregnancy. Traditionally, this p…